Optimize AI generation speed and add richer insight data

Speed optimizations:
- Add session.prewarm() in InsightsViewModel and ReportsViewModel init
  for 40% faster first-token latency
- Cap maximumResponseTokens on all 8 AI respond() calls (100-600 per use case)
- Add prompt brevity constraints ("1-2 sentences", "2 sentences")
- Reduce report batch concurrency from 4 to 2 to prevent device contention
- Pre-fetch health data once and share across all 3 insight periods

Richer insight data in MoodDataSummarizer:
- Tag-mood correlations: overall frequency + good day vs bad day tag breakdown
- Weather-mood correlations: avg mood by condition and temperature range
- Absence pattern detection: logging gap count with pre/post-gap mood averages
- Entry source breakdown: % of entries from App, Widget, Watch, Siri, etc.
- Update insight prompt to leverage tags, weather, and gap data when available

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Shared/Services/FoundationModelsReflectionService.swift

@@ -28,14 +28,12 @@ class FoundationModelsReflectionService {
         mood: Mood
     ) async throws -> AIReflectionFeedback {
         let session = LanguageModelSession(instructions: systemInstructions)
-
         let prompt = buildPrompt(from: reflection, mood: mood)
-
         let response = try await session.respond(
             to: prompt,
-            generating: AIReflectionFeedback.self
+            generating: AIReflectionFeedback.self,
+            options: GenerationOptions(maximumResponseTokens: 200)
         )
-
         return response.content
     }